Laser cutting machine control method and control system

Abstract

The invention relates to the technical field of laser cutting, and provides a laser cutting machine control method and system.The method comprises the following steps that parameters of a to-be-cut workpiece are obtained, and a cutting path area is obtained according to the parameters of the to-be-cut workpiece; obtaining a cutting path area image, and obtaining multi-dimensional defect information of a cutting path area according to the cutting path area image; obtaining an optimal cutting path according to the multi-dimensional defect information of the cutting path area; and according to the optimal cutting path, the laser cutting machine is controlled to act, and the to-be-cut workpiece is subjected to laser cutting treatment. On the basis that the cut workpiece conforms to the required shape and size, defects and flaws on the surface of the cut workpiece are reduced as much as possible, so that the appearance quality of the surface of the cut workpiece is optimized, and the problems that when an existing laser cutting machine conducts cutting path planning on the workpiece, only the shape and size requirements are usually considered, and the working efficiency is low are solved. And defects existing on the surface of the workpiece are ignored, so that the surface of the cut workpiece is not good.

Description

Technical Field

[0001] The present invention relates to the field of laser cutting technology, and in particular to a laser cutting machine control method and control system. Background Art

[0002] Laser cutting is a technology that uses a focused high-power density laser beam to irradiate the workpiece, causing the irradiated material to melt, vaporize, ablate or reach the ignition point quickly, and at the same time uses a high-speed airflow coaxial with the beam to blow away the molten material, thereby achieving the cutting of the workpiece. The laser cutting machine system is generally composed of a laser generator, a beam transmission component, a workbench, a microcomputer numerical control cabinet, a cooler, and a computer (hardware and software). Through laser cutting technology, the workpiece can be cut into the desired shape and size. The cutting objects include metal profiles, plates, plastics, quartz, ceramics, etc.

[0003] For some workpieces, such as ceramics, wood panels, and aluminum profiles, their cutting shapes and sizes are not unique. When existing laser cutting machines plan the cutting path for the above workpieces, they often only consider the shape and size requirements, ignoring the defects on the surface of the workpiece, which can easily cause the problem of poor surface quality of the workpiece after cutting. For this reason, it is necessary to develop a laser cutting machine control method to plan the cutting path according to the surface defects of the workpiece to be cut, so that the surface appearance quality of the workpiece after cutting is optimized on the basis of meeting the required shape and size. Summary of the invention

[0004] Based on this, in order to solve the problem that when the existing laser cutting machine plans the cutting path for the workpiece, it often only considers the shape and size requirements and ignores the defects on the workpiece surface, which easily causes the poor surface of the workpiece after cutting, the present invention provides a laser cutting machine control method and control system, which can obtain the cutting path area according to the parameters of the workpiece to be cut, and obtain the multi-dimensional defect information of the cutting path area according to the cutting path area image, and then obtain the optimal cutting path, so that the workpiece after cutting can optimize the surface appearance quality of the workpiece after cutting as much as possible on the basis of meeting the required shape and size. The specific technical scheme is as follows:

[0005] A laser cutting machine control method comprises the following steps:

[0006] Acquire parameters of a workpiece to be cut, and acquire a cutting path area according to the parameters of the workpiece to be cut;

[0007] Acquire a cutting path area image, and acquire multi-dimensional defect information of the cutting path area according to the cutting path area image;

[0008] Acquire an optimal cutting path according to the multi-dimensional defect information of the cutting path area;

[0009] According to the optimal cutting path, the laser cutting machine is controlled to perform laser cutting on the workpiece to be cut.

[0010] The laser cutting machine control method obtains the cutting path area and the multi-dimensional defect information of the cutting path area, and obtains the optimal cutting path according to the multi-dimensional defect information of the cutting path area. It can reduce the defects and flaws on the surface of the workpiece after cutting as much as possible on the basis of ensuring that the workpiece after cutting meets the required shape and size, thereby optimizing the surface appearance quality of the workpiece after cutting. It solves the problem that when the existing laser cutting machine plans the cutting path for the workpiece, it often only considers the shape and size requirements and ignores the defects on the workpiece surface, which easily causes the poor surface of the workpiece after cutting.

[0011] Preferably, the specific method for obtaining the cutting path area according to the parameters of the workpiece to be cut comprises the following steps:

[0012] Acquire an initial cutting path and an allowable deviation range according to the parameters of the workpiece to be cut;

[0013] A cutting path area is acquired according to the initial cutting path and the allowable deviation range.

[0014] Preferably, the specific method for obtaining the optimal cutting path according to the multi-dimensional defect information of the cutting path area comprises the following steps:

[0015] Constructing a multidimensional defect index function

[0016] Obtaining an optimal cutting path according to the multidimensional defect index function to minimize DefectIndex×γ1+ΔD×γ2;

[0017] Where n represents the number of dimensions of multidimensional defect information, λ i represents the defect characteristic value of the i-th dimension, α i represents the defect feature adjustment coefficient of the i-th dimension, C i represents the defect feature correction value of the i-th dimension, ΔD represents the deviation distance between the optimal cutting path and the initial cutting path, γ1 and γ2 represent the multidimensional defect index adjustment coefficient and the deviation distance adjustment coefficient, respectively.

[0018] Preferably, the laser cutting machine control method further comprises visually calibrating a camera for acquiring an image of the cutting path area, and the visual calibration method comprises the following steps:

[0019] Obtain the number of standard calibration images p, the calibration plate accuracy ca, the preset standard calibration accuracy sca, the standard cutting error scd, the preset cutting error pcd, the reprojection error threshold Ree' and the reprojection error estimate Ree;

[0020] Calculating the total number of calibration images according to the number of standard calibration images, the accuracy of the calibration plate, the preset standard calibration accuracy, the standard cutting error, the preset cutting error, and the estimated value of the reprojection error;

[0021] According to the total number of calibration images, a plurality of actual calibration images are collected by the camera, and the camera is calibrated according to the plurality of actual calibration images to obtain estimated values ​​of internal and external parameters;

[0022] The estimated values ​​of internal and external parameters are optimized multiple times through iterative optimization method until the reprojection error value is minimized;

[0023] Obtain optimal internal and external parameter estimates, and calibrate the camera according to the optimal internal and external parameter estimates.

[0024] Preferably, according to the formula

[0025] Calculating the total number of calibration images;

[0026] Wherein, β1, β2, β3 represent the first calibration coefficient, the second calibration coefficient, and the third calibration coefficient, respectively, e represents a natural constant, CF represents an image calibration correction factor, and [] represents a rounding function.

[0027] Preferably, the specific method of performing multiple iterations of optimization on the estimated values ​​of the internal and external parameters by an iterative optimization method until the reprojection error value is minimized comprises the following steps:

[0028] The estimated values ​​of the internal and external parameters are optimized multiple times by iterative optimization method until the maximum number of iterations is reached or the reprojection error value is less than the preset threshold;

[0029] Among them, the maximum number of iterations m is a preset constant, Represents the ceiling function.

[0030] A laser cutting machine control system, used to implement the laser cutting machine control method, comprising:

[0031] A path area acquisition module, used to acquire parameters of a workpiece to be cut, and to acquire a cutting path area according to the parameters of the workpiece to be cut;

[0032] A multi-dimensional information acquisition module, used to acquire a cutting path area image, and acquire multi-dimensional defect information of the cutting path area according to the cutting path area image;

[0033] An optimal path acquisition module, used for acquiring an optimal cutting path according to multi-dimensional defect information of the cutting path area;

[0034] The control module is used to control the action of the laser cutting machine according to the optimal cutting path to perform laser cutting processing on the workpiece to be cut.

[0035] Preferably, the path area acquisition module includes:

[0036] A first path acquisition unit, used for acquiring an initial cutting path and an allowable deviation range according to the parameters of the workpiece to be cut;

[0037] The second path acquisition unit is used to acquire a cutting path area according to the initial cutting path and the allowable deviation range.

[0038] Preferably, the optimal path acquisition module includes:

[0039] A function building unit, used to build a multi-dimensional defect index function;

[0040] A path calculation unit, used for obtaining an optimal cutting path according to the multi-dimensional defect index function to minimize DefectIndex×γ1+ΔD×γ2;

[0041] Where n represents the number of dimensions of multidimensional defect information, λ i represents the defect characteristic value of the i-th dimension, α i represents the defect feature adjustment coefficient of the i-th dimension, C i represents the defect feature correction value of the i-th dimension, ΔD represents the deviation distance between the optimal cutting path and the initial cutting path, γ1 and γ2 represent the multidimensional defect index adjustment coefficient and the deviation distance adjustment coefficient, respectively.

[0042] Preferably, the laser cutting machine control system further includes:

[0043] A parameter acquisition module is used to obtain the number of standard calibration images, calibration plate accuracy, preset standard calibration accuracy, standard cutting error, preset cutting error, reprojection error threshold and reprojection error estimate;

[0044] An image total number calculation module, used to calculate the total number of calibration images according to the number of standard calibration images, the accuracy of the calibration plate, the preset standard calibration accuracy, the standard cutting error, the preset cutting error and the estimated value of the reprojection error;

[0045] An intrinsic and extrinsic parameter calculation module, used to collect a plurality of actual calibration images through the camera according to the total number of calibration images, and calibrate the camera according to the plurality of actual calibration images to obtain intrinsic and extrinsic parameter estimation values;

[0046] An iterative optimization module is used to perform multiple iterations of optimization on the estimated values ​​of the internal and external parameters by an iterative optimization method until the reprojection error value is minimized;

[0047] The calibration module is used to obtain the optimal internal and external parameter estimation values, and calibrate the camera according to the optimal internal and external parameter estimation values. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0049] Figure 1 It is a schematic diagram of the overall flow of a laser cutting machine control method in one embodiment of the present invention;

[0050] Figure 2 is a flowchart of a specific method for obtaining a cutting path area in one embodiment of the present invention;

[0051] Figure 3 is a schematic diagram of a process of visually calibrating a camera in one embodiment of the present invention;

[0052] Figure 4 It is a schematic diagram of the overall structure of a laser cutting machine control method in one embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the protection scope of the present invention.

[0054] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0056] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0057] For some workpieces, such as tiles, aluminum profiles, aluminum-plastic panels, and some decorative panels, if there are defects such as cracks, spots, bumps, holes, and dirt on the surface, the surface appearance quality will be reduced. With the development of laser cutting machine technology, laser cutting is more and more widely used in the cutting of the above workpieces. For many factories, different customers often have certain differences in the size and shape requirements of the workpieces. In this way, when using laser cutting workpieces, different workpiece cutting shape and size requirements can be considered, and the cutting path can be adjusted as reasonably as possible. On the basis of making the workpiece after cutting meet the required shape and size, the surface appearance quality of the workpiece after cutting is optimized to the greatest extent.

[0058] Existing laser cutting machines, when planning the cutting path for a workpiece, often only consider the shape and size requirements, ignoring the defects on the workpiece surface, which can easily lead to poor surface quality of the workpiece after cutting. Even though some laser cutting machines will use visual recognition technology to identify defects on the workpiece surface before cutting, they mostly just screen out the workpieces with defects, and do not comprehensively consider the different shapes and sizes required for workpiece cutting and the acceptable degree of defects to optimize the cutting path, so as to obtain a workpiece that meets both the required shape and size requirements and the acceptable degree of defects.

[0059] In order to solve the technical problems existing in the above-mentioned prior art, Figure 1 As shown, the present invention provides a laser cutting machine control method, which includes the following steps:

[0060] S1, obtaining parameters of a workpiece to be cut, and obtaining a cutting path area according to the parameters of the workpiece to be cut.

[0061] The parameters of the workpiece to be cut include but are not limited to the type of the workpiece to be cut, the shape and size of the cut, and the error range.

[0062] The laser cutting machine at least includes a laser generator, a beam transmission component, a workbench, a microcomputer numerical control cabinet and a central controller. It controls the laser generator to output a laser beam to cut the workpiece into a desired shape and size. The cutting objects include but are not limited to metal profiles, plates, plastics, quartz, and ceramics. Since the specific structure of the above laser cutting machine belongs to the conventional technical means in this field, it will not be described here.

[0063] Preferably, if Figure 2 As shown, the specific method for obtaining the cutting path area according to the parameters of the workpiece to be cut includes the following steps:

[0064] S10, obtaining an initial cutting path and an allowable deviation range according to the parameters of the workpiece to be cut; for the initial cutting path, the image and edge contour of the workpiece to be cut can be obtained first, and at least one initial cutting path can be obtained by combining the image, edge contour and specific cutting shape and size of the workpiece to be cut. The workpiece to be cut is cut along the initial cutting path, and a workpiece that meets the specific cutting shape and size requirements can be obtained. The allowable deviation range can be determined based on a preset cutting error, for example, if the preset cutting error is expressed as ±ε, then the allowable deviation range is ±ε, and it can also be set by a technician based on actual conditions and experience.

[0065] S11, obtaining a cutting path area according to the initial cutting path and an allowable deviation range.

[0066] Specifically, if the initial cutting path is represented by a curve or a straight line function y=f(x), and the allowable deviation range is ±ε, then the cutting path area can be expressed as f(x)±ε, which can be understood as the area enclosed by the two cutting paths obtained after y=f(x) is translated by ±ε.

[0067] S2, obtaining a cutting path area image, and obtaining multi-dimensional defect information of the cutting path area according to the cutting path area image. The multi-dimensional defect information includes but is not limited to cracks, burrs, holes, dirt, protrusions and deformations, which are specifically related to the type of workpiece to be cut. Since it is based on visual image recognition technology, recognizing the multi-dimensional defect information of the cutting path area according to the cutting path area image belongs to conventional technical means in the field, it will not be repeated here.

[0068] S3, obtaining an optimal cutting path according to the multi-dimensional defect information of the cutting path area.

[0069] Preferably, the specific method for obtaining the optimal cutting path according to the multi-dimensional defect information of the cutting path area comprises the following steps:

[0070] S30, constructing a multidimensional defect index function

[0071] S31, obtaining an optimal cutting path according to the multidimensional defect index function to minimize DefectIndex×γ1+ΔD×γ2;

[0072] Where n represents the number of dimensions of multidimensional defect information, λ i represents the defect characteristic value of the i-th dimension, α i represents the defect feature adjustment coefficient of the i-th dimension, C irepresents the defect feature correction value of the i-th dimension, ΔD represents the deviation distance between the optimal cutting path and the initial cutting path, γ1 and γ2 represent the multidimensional defect index adjustment coefficient and the deviation distance adjustment coefficient respectively, and DefectIndex represents the multidimensional defect index.

[0073] The defect feature correction value of the i-th dimension can be set by a technician. Preferably, the defect feature correction value of the i-th dimension is calculated based on the actual reprojection error after camera calibration. The method for obtaining the defect feature value is: based on image recognition technology, the defect contour line in the cutting path area is obtained, the defect area is calculated according to the defect contour line, and the defect area is used as the defect feature value. The deviation distance is obtained by calculating the average distance between multiple sampling points between the optimal cutting path and the initial cutting path, or by constructing XY axis coordinates and placing the optimal cutting path and the initial cutting path in the XY axis coordinate system, and calculating the integral area difference between the optimal cutting path and the initial cutting path, and using the integral area difference as the deviation distance.

[0074] Taking MIN DefectIndex×γ1+ΔD×γ2 as the condition for obtaining the optimal cutting path, the optimal cutting path is obtained to minimize DefectIndex×γ1+ΔD×γ2. The optimal cutting path will enable the workpiece after cutting to meet the required shape and size, while minimizing the defects on the surface of the workpiece after cutting, thereby optimizing the surface appearance quality of the workpiece after cutting. Since the multi-dimensional defect index adjustment coefficient and the deviation distance adjustment coefficient are set, the deviation distance between the shape and size of the workpiece after cutting and the shape and size corresponding to the initial cutting path and the weight of the surface defects of the craftsman after final cutting can also be adjusted according to actual conditions through the formula DefectIndex×γ1+ΔD×γ2, and the different shape and size required for workpiece cutting and the acceptable degree of defects are comprehensively considered to optimize the cutting path, thereby obtaining a workpiece that meets the required shape and size requirements and the acceptable degree of defects, thereby improving flexibility and wide applicability.

[0075] Preferably, the optimal cutting path is obtained according to the multidimensional defect index function, so that DefectIndex×γ1+ΔD×γ2 is minimized, and the multidimensional defect index DefectIndex meets the preset acceptable defect level requirements. The acceptable defect level requirements can be pre-set by technicians in the form of a multidimensional defect index. In this way, the method can comprehensively consider the different shapes and sizes required for workpiece cutting and the acceptable defect levels to optimize the cutting path, thereby obtaining a workpiece that meets both the required shape and size requirements and the acceptable defect level requirements.

[0076] S4, controlling the laser cutting machine to operate according to the optimal cutting path, and performing laser cutting processing on the workpiece to be cut along the optimal cutting path.

[0077] Preferably, after the workpiece to be cut is subjected to laser cutting processing, the quality of the workpiece can also be graded according to the size of DefectIndex×γ1+ΔD×γ2, so as to perform different subsequent processing on the cut workpiece. It combines the size of the multi-dimensional defect index of the workpiece after cutting and the actual deviation of the shape and size corresponding to the initial cutting path, providing a new idea for classifying the quality of cut workpieces.

[0078] The laser cutting machine control method obtains the cutting path area and the multi-dimensional defect information of the cutting path area, and obtains the optimal cutting path according to the multi-dimensional defect information of the cutting path area. It can reduce the defects and flaws on the surface of the workpiece after cutting as much as possible on the basis of making the workpiece after cutting meet the required shape and size, thereby optimizing the surface appearance quality of the workpiece after cutting. It solves the problem that when the existing laser cutting machine plans the cutting path for the workpiece, it often only considers the shape and size requirements and ignores the defects on the surface of the workpiece, which easily causes the surface of the workpiece to be poor after cutting. In addition, the laser cutting machine control method comprehensively considers the different shapes and sizes required for workpiece cutting and the acceptable degree of defects to optimize the cutting path, and can obtain a workpiece that meets both the required shape and size requirements and the acceptable degree of defects.

[0079] Camera calibration is the basis of visual measurement. Its accuracy will affect the accuracy of the shape and size of the workpiece after cutting along the optimal cutting path and the defect feature values ​​collected based on visual image technology, which directly affects the overall performance of the system.

[0080] Existing laser control systems generally calibrate the system’s camera through a calibration plate. In camera calibration, the accuracy of feature point detection is one of the important factors affecting the reprojection error. If the feature point detection is inaccurate, it will lead to a large reprojection error, thus affecting the accuracy of the calibration result. The estimation accuracy of the camera’s intrinsic parameters and distortion coefficients has a direct impact on the reprojection error. The number and quality of calibration images will also affect the reprojection error. The more calibration images there are, the wider the field of view covered, and more accurate camera parameter estimates can usually be obtained. Therefore, the accuracy of feature point detection can be improved by increasing the number of calibration images, thereby reducing the reprojection error and improving the accuracy of camera calibration. The increase in the number of calibration images means that more image acquisition processing time and computing resources are required.

[0081] In order to balance the system's visual measurement accuracy requirements and image acquisition processing time and computing resource requirements, and improve the overall performance of the system, as a preferred technical solution, such as Figure 3As shown, the laser cutting machine control method further includes visually calibrating a camera that acquires an image of a cutting path area, and the visual calibration method includes the following steps:

[0082] S5, obtaining the number of standard calibration images p, the calibration plate accuracy ca, the preset standard calibration accuracy sca, the standard cutting error scd, the preset cutting error pcd, the reprojection error threshold Ree' and the reprojection error estimate Ree.

[0083] The number of standard calibration images, the preset standard calibration accuracy, the standard cutting error, the preset cutting error, the reprojection error threshold and the reprojection error estimate can all be set by a technician. The calibration plate accuracy is obtained based on the accuracy parameters of the actual calibration plate used for camera calibration.

[0084] S6, calculating the total number of calibration images according to the number of standard calibration images, the calibration plate accuracy, the preset standard calibration accuracy, the standard cutting error, the preset cutting error and the reprojection error estimate.

[0085] Preferably, according to the formula

[0086] Calculate the total number of calibration images; wherein β1, β2, and β3 represent the first calibration coefficient, the second calibration coefficient, and the third calibration coefficient, respectively, which can be set and adjusted by a technician, e represents a natural constant, CF represents an image calibration correction factor, [] represents a rounding function, and CalibrationPictureTotal represents the total number of calibration images.

[0087] For the image calibration correction factor, we first obtain the difference between the real-time parameter characteristic values ​​of multiple external environmental factors that affect the reprojection error, such as system temperature, vibration value, temperature and humidity value, and light brightness, and the preset standard characteristic values, then calculate the ratio between the difference and the preset standard characteristic value, and finally obtain it by calculating the weighted average of the ratio.

[0088] By setting the image calibration correction factor and taking the influence of external factors on the reprojection error into account, the accuracy of camera calibration can be improved and more in line with the actual situation.

[0089] S7, according to the total number of calibration images, collecting a plurality of actual calibration images through the camera, and calibrating the camera according to the plurality of actual calibration images to obtain estimated values ​​of intrinsic and extrinsic parameters.

[0090] Since calibrating the camera through the calibration image and obtaining the estimated values ​​of the internal and external parameters belong to conventional technical means in the field, they will not be described in detail here.

[0091] S8, performing multiple iterations of optimization on the estimated values ​​of the internal and external parameters through an iterative optimization method until the reprojection error value is minimized.

[0092] Here, the iterative optimization method includes but is not limited to the least squares method and the gradient descent method.

[0093] Preferably, the specific method of performing multiple iterative optimization on the estimated values ​​of the internal and external parameters by an iterative optimization method until the reprojection error value is minimized includes the following steps: performing multiple iterative optimization on the estimated values ​​of the internal and external parameters by an iterative optimization method until the maximum number of iterations is reached or the reprojection error value is less than a preset threshold.

[0094] Among them, the maximum number of iterations m is a preset constant, The maximum number of iterations is associated with the total number of calibrated images and is proportional to the total number of calibrated images. By setting a reasonable preset constant m, a suitable maximum number of iterations can be obtained to avoid the risk of overfitting and waste of computing resources caused by too large a number of iterations, and the risk of underfitting caused by too small a number of iterations.

[0095] S9, obtaining optimal internal and external parameter estimation values, and calibrating the camera according to the optimal internal and external parameter estimation values. Specifically, the optimal internal and external parameter estimation values ​​can be obtained according to the minimized reprojection error value after multiple iterations of optimization of the internal and external parameter estimation values.

[0096] The total number of calibration images is calculated by the number of standard calibration images, the accuracy of the calibration plate, the preset standard calibration accuracy, the standard cutting error, the preset cutting error and the estimated value of the reprojection error. According to the total number of calibration images, a plurality of actual calibration images are collected by the camera, and then the camera is calibrated according to the plurality of actual calibration images to obtain estimated values ​​of internal and external parameters, and the optimal estimated values ​​of internal and external parameters are obtained to calibrate the camera. It comprehensively weighs a plurality of different factors, and can appropriately balance and meet the image acquisition processing time and computing resource requirements on the basis of meeting the visual measurement accuracy requirements of the system, thereby improving the overall comprehensive performance of the system.

[0097] As a preferred technical solution, the defect feature correction value of the i-th dimension is calculated based on the actual reprojection error after camera calibration, that is, based on the minimized reprojection error value after multiple iterative optimization of the internal and external parameter estimation values. Specifically, the defect feature correction value of the i-th dimension is equal to the product of the minimized reprojection error value and the preset defect feature correction weight coefficient of the i-th dimension.

[0098] Since the actual reprojection error is related to the camera calibration accuracy, calculating the defect feature correction value of the i-th dimension based on the actual reprojection error after camera calibration can indirectly improve the accuracy of the multidimensional defect index, thereby making the optimal cutting path more accurate.

[0099] The present invention also provides a laser cutting machine control system for implementing the laser cutting machine control method. Figure 4 As shown, it includes a path area acquisition module, a multi-dimensional information acquisition module, an optimal path acquisition module and a control module.

[0100] The path area acquisition module is used to acquire the parameters of the workpiece to be cut, and acquire the cutting path area according to the parameters of the workpiece to be cut; preferably, the path area acquisition module includes a first path acquisition unit and a second path acquisition unit, the first path acquisition unit is used to acquire the initial cutting path and the allowable deviation range according to the parameters of the workpiece to be cut, and the second path acquisition unit is used to acquire the cutting path area according to the initial cutting path and the allowable deviation range.

[0101] The allowable deviation range can be determined based on the preset cutting error. For example, if the preset cutting error is expressed as ±ε, the allowable deviation range is ±ε. It can also be set by technicians based on actual conditions and experience. If the initial cutting path is expressed as a curve or straight line function y=f(x), the allowable deviation range is ±ε, then the cutting path area can be expressed as f(x)±ε, which can be understood as the area enclosed by the two cutting paths obtained after y=f(x) is translated by ±ε.

[0102] The multidimensional information acquisition module is used to obtain a cutting path area image, and obtain multidimensional defect information of the cutting path area based on the cutting path area image; the multidimensional defect information includes but is not limited to cracks, burrs, holes, dirt, protrusions and deformations, which is specifically related to the type of workpiece to be cut.

[0103] The optimal path acquisition module is used to acquire the optimal cutting path according to the multi-dimensional defect information of the cutting path area; the control module is used to control the action of the laser cutting machine according to the optimal cutting path to perform laser cutting processing on the workpiece to be cut.

[0104] Preferably, the optimal path acquisition module includes a function construction unit and a path calculation unit. The function construction unit is used to construct a multidimensional defect index function, and the multidimensional defect index function is expressed as The path calculation unit is used to obtain the optimal cutting path according to the multi-dimensional defect index function to minimize DefectIndex×γ1+ΔD×γ2.

[0105] Where n represents the number of dimensions of multidimensional defect information, λ irepresents the defect characteristic value of the i-th dimension, α i represents the defect feature adjustment coefficient of the i-th dimension, C i represents the defect feature correction value of the i-th dimension, ΔD represents the deviation distance between the optimal cutting path and the initial cutting path, γ1 and γ2 represent the multidimensional defect index adjustment coefficient and the deviation distance adjustment coefficient.

[0106] DefectIndex×γ1+ΔD×γ2 is used as the condition for obtaining the optimal cutting path, and the optimal cutting path is obtained to minimize DefectIndex×γ1+ΔD×γ2. The optimal cutting path will enable the workpiece after cutting to meet the required shape and size, while minimizing the defects on the surface of the workpiece after cutting, thereby optimizing the surface appearance quality of the workpiece after cutting. Since the multi-dimensional defect index adjustment coefficient and the deviation distance adjustment coefficient are set, the deviation distance between the shape and size of the workpiece after cutting and the shape and size corresponding to the initial cutting path and the weight of the surface defects of the craftsman after final cutting can also be adjusted according to actual conditions through the formula DefectIndex×γ1+ΔD×γ2, which improves flexibility and wide applicability.

[0107] The laser cutting machine control system obtains the cutting path area and multi-dimensional defect information of the cutting path area, and obtains the optimal cutting path according to the multi-dimensional defect information of the cutting path area. It can minimize the defects and flaws on the surface of the workpiece after cutting while ensuring that the workpiece after cutting meets the required shape and size, thereby optimizing the surface appearance quality of the workpiece after cutting. It solves the problem that when the existing laser cutting machine plans the cutting path for the workpiece, it often only considers the shape and size requirements and ignores the defects on the workpiece surface, which easily causes the poor surface of the workpiece after cutting.

[0108] As a preferred technical solution, the laser cutting machine control system also includes a parameter acquisition module, an image total number calculation module, an internal and external parameter calculation module, an iterative optimization module and a calibration module.

[0109] The parameter acquisition module is used to acquire the number of standard calibration images, the calibration plate accuracy, the preset standard calibration accuracy, the standard cutting error, the preset cutting error, the reprojection error threshold value and the reprojection error estimate value; the total number of images calculation module is used to calculate the total number of calibration images according to the number of standard calibration images, the calibration plate accuracy, the preset standard calibration accuracy, the standard cutting error, the preset cutting error and the reprojection error estimate value;

[0110] Specifically, the total number of calibration images Among them, β1, β2, and β3 represent the first calibration coefficient, the second calibration coefficient, and the third calibration coefficient, respectively, which can be set and adjusted by technical personnel, e represents a natural constant, CF represents an image calibration correction factor, and [] represents a rounding function.

[0111] By setting the image calibration correction factor and taking the influence of external factors on the reprojection error into account, the accuracy of camera calibration can be improved and more in line with the actual situation.

[0112] The internal and external parameter calculation module is used to collect multiple actual calibration images through the camera according to the total number of calibration images, and calibrate the camera according to the multiple actual calibration images to obtain internal and external parameter estimation values; the iterative optimization module is used to iteratively optimize the internal and external parameter estimation values ​​multiple times through an iterative optimization method until the reprojection error value is minimized.

[0113] Preferably, the estimated values ​​of the internal and external parameters are iteratively optimized multiple times by an iterative optimization method until a maximum number of iterations is reached or the reprojection error value is less than a preset threshold.

[0114] Among them, the maximum number of iterations m is a preset constant, Represents the ceiling function.

[0115] The calibration module is used to obtain optimal internal and external parameter estimation values, and calibrate the camera according to the optimal internal and external parameter estimation values.

[0116] The total number of calibration images is calculated by the number of standard calibration images, the accuracy of the calibration plate, the preset standard calibration accuracy, the standard cutting error, the preset cutting error and the estimated value of the reprojection error. According to the total number of calibration images, a plurality of actual calibration images are collected by the camera, and then the camera is calibrated according to the plurality of actual calibration images to obtain estimated values ​​of internal and external parameters, and the optimal estimated values ​​of internal and external parameters are obtained to calibrate the camera. It comprehensively weighs a plurality of different factors, and can appropriately balance and meet the image acquisition processing time and computing resource requirements on the basis of meeting the visual measurement accuracy requirements of the system, thereby improving the overall comprehensive performance of the system.

[0117] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A laser cutting machine control method, characterized in that: The laser cutting machine control method comprises the following steps: Acquire parameters of a workpiece to be cut, and acquire a cutting path area according to the parameters of the workpiece to be cut; Acquire a cutting path area image, and acquire multi-dimensional defect information of the cutting path area according to the cutting path area image; Acquire an optimal cutting path according to the multi-dimensional defect information of the cutting path area; According to the optimal cutting path, the laser cutting machine is controlled to perform laser cutting on the workpiece to be cut.

2. A laser cutting machine control method as claimed in claim 1, characterized in that: The specific method for obtaining the cutting path area according to the parameters of the workpiece to be cut comprises the following steps: Acquire an initial cutting path and an allowable deviation range according to the parameters of the workpiece to be cut; A cutting path area is acquired according to the initial cutting path and the allowable deviation range.

3. A laser cutting machine control method as claimed in claim 2, characterized in that: The specific method for obtaining the optimal cutting path according to the multi-dimensional defect information of the cutting path area comprises the following steps: Constructing a multidimensional defect index function Obtaining an optimal cutting path according to the multidimensional defect index function to minimize DefectIndex×γ1+ΔD×γ2; Where n represents the number of dimensions of multidimensional defect information, λ i represents the defect characteristic value of the i-th dimension, α i represents the defect feature adjustment coefficient of the i-th dimension, C i represents the defect feature correction value of the i-th dimension, ΔD represents the deviation distance between the optimal cutting path and the initial cutting path, γ1 and γ2 represent the multidimensional defect index adjustment coefficient and the deviation distance adjustment coefficient, respectively.

4. A laser cutting machine control method as claimed in claim 3, characterized in that: The laser cutting machine control method further includes visually calibrating a camera that acquires an image of a cutting path area, and the visual calibration method includes the following steps: Obtain the number of standard calibration images p, the calibration plate accuracy ca, the preset standard calibration accuracy sca, the standard cutting error scd, the preset cutting error pcd, the reprojection error threshold Ree' and the reprojection error estimate Ree; Calculating the total number of calibration images according to the number of standard calibration images, the accuracy of the calibration plate, the preset standard calibration accuracy, the standard cutting error, the preset cutting error, and the estimated value of the reprojection error; According to the total number of calibration images, a plurality of actual calibration images are collected by the camera, and the camera is calibrated according to the plurality of actual calibration images to obtain estimated values ​​of internal and external parameters; The estimated values ​​of internal and external parameters are optimized multiple times through iterative optimization method until the reprojection error value is minimized; Obtain optimal internal and external parameter estimates, and calibrate the camera according to the optimal internal and external parameter estimates.

5. A laser cutting machine control method as claimed in claim 4, characterized in that: According to the formula Calculate the total number of calibration images CalibrationPictureTotal; Wherein, β1, β2, β3 represent the first calibration coefficient, the second calibration coefficient, and the third calibration coefficient, respectively, e represents a natural constant, CF represents an image calibration correction factor, and [] represents a rounding function.

6. A laser cutting machine control method as claimed in claim 5, characterized in that: The specific method of performing multiple iterations of optimization on the estimated values ​​of the internal and external parameters by an iterative optimization method until the reprojection error value is minimized includes the following steps: The estimated values ​​of the internal and external parameters are optimized multiple times by iterative optimization method until the maximum number of iterations is reached or the reprojection error value is less than the preset threshold; Among them, the maximum number of iterations m is a preset constant, Represents the ceiling function.

7. A laser cutting machine control system, used to implement the laser cutting machine control method according to any one of claims 1 to 6, characterized in that: The laser cutting machine control system includes: A path area acquisition module, used to acquire parameters of a workpiece to be cut, and to acquire a cutting path area according to the parameters of the workpiece to be cut; A multi-dimensional information acquisition module, used to acquire a cutting path area image, and acquire multi-dimensional defect information of the cutting path area according to the cutting path area image; An optimal path acquisition module, used for acquiring an optimal cutting path according to multi-dimensional defect information of the cutting path area; The control module is used to control the action of the laser cutting machine according to the optimal cutting path to perform laser cutting processing on the workpiece to be cut.

8. A laser cutting machine control system as claimed in claim 7, characterized in that: The path area acquisition module includes: A first path acquisition unit, used for acquiring an initial cutting path and an allowable deviation range according to the parameters of the workpiece to be cut; The second path acquisition unit is used to acquire a cutting path area according to the initial cutting path and the allowable deviation range.

9. A laser cutting machine control system as claimed in claim 8, characterized in that: The optimal path acquisition module includes: A function building unit, used to build a multi-dimensional defect index function; A path calculation unit, used for obtaining an optimal cutting path according to the multi-dimensional defect index function to minimize DefectIndex×γ1+ΔD×γ2; Where n represents the number of dimensions of multidimensional defect information, λ i represents the defect characteristic value of the i-th dimension, α i represents the defect feature adjustment coefficient of the i-th dimension, C i represents the defect feature correction value of the i-th dimension, ΔD represents the deviation distance between the optimal cutting path and the initial cutting path, γ1 and γ2 represent the multidimensional defect index adjustment coefficient and the deviation distance adjustment coefficient, respectively.

10. A laser cutting machine control system as claimed in claim 9, characterized in that: The laser cutting machine control system also includes: A parameter acquisition module is used to obtain the number of standard calibration images, calibration plate accuracy, preset standard calibration accuracy, standard cutting error, preset cutting error, reprojection error threshold and reprojection error estimate; An image total number calculation module, used to calculate the total number of calibration images according to the number of standard calibration images, the accuracy of the calibration plate, the preset standard calibration accuracy, the standard cutting error, the preset cutting error and the estimated value of the reprojection error; An intrinsic and extrinsic parameter calculation module, used to collect a plurality of actual calibration images through the camera according to the total number of calibration images, and calibrate the camera according to the plurality of actual calibration images to obtain intrinsic and extrinsic parameter estimation values; An iterative optimization module is used to perform multiple iterations of optimization on the estimated values ​​of the internal and external parameters by an iterative optimization method until the reprojection error value is minimized; The calibration module is used to obtain the optimal internal and external parameter estimation values, and calibrate the camera according to the optimal internal and external parameter estimation values.

Images